© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72489
    Prev
    Next
    INDEX
    Explanations

    potential energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$?
    -1.00
    _;
    -0.98
    ud
    -0.94
    Y
    -0.94
    td
    -0.91
     likes
    -0.91
    ляция
    -0.91
     —
    -0.91
    EN
    -0.89
    vikle
    -0.88
    POSITIVE LOGITS
     ESTADO
    1.04
    dž
    0.99
    schwarz
    0.97
    وین
    0.96
     terwijl
    0.95
     résistance
    0.90
    作品の
    0.90
    gucigalpa
    0.90
     数据库
    0.90
    別の
    0.90
    Activations Density 0.109%

    No Known Activations